rerun primates

covid_comp_bats.Rnw

@@ -62,8 +62,6 @@ y=as.numeric(as.character(outlier$bats_omegaM0codeml)),
 outlier$Gene.name)
 @
 
-\subsection{Cooper-bats VS Hawkins-bats and DGINN-bats VS Hawkins-bats}
-
 \section{Overlap}
 
 \subsection{Data}
@@ -159,11 +157,8 @@ dftmp<-tab[,c("bats_File", "bats_Name",
 
 names(dftmp)<-names(df)
 makeFig1(dftmp)
-
 @
 
-
-
 \end{document}
 
 

covid_comp_primate.Rnw

@@ -30,108 +30,166 @@
 Analysis were formatted by the script covid\_comp\_script0\_table.Rnw.
 
 <<>>=
-workdir<-"/home/adminmarie/Documents/CIRI_BIBS_projects/2020_05_Etienne_covid/"
+home<-"/home/adminmarie/Documents/"
+workdir<-paste0(home, "CIRI_BIBS_projects/2020_05_Etienne_covid/")
 
 tab<-read.delim(paste0(workdir, 
   "covid_comp/covid_comp_complete.txt"), h=T, sep="\t")
 dim(tab)
-tab$Gene.name<-as.character(tab$Gene.name)
+tab$Gene.name<-as.character(tab$Gene.name.x)
 tab$Gene.name[tab$PreyGene=="MTARC1"]<-"MTARC1"
-
 @
 
-
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
 \section{Comparisons Primates}
 
 \subsection{Janet Young's results (Young-primate) VS DGINN-full's results}
 
 Comparaison des Omega: colonne L "whole.gene.dN.dS.model.0" VS colonne "omega" dans la sortie de dginn.
-<<omegaM7M8_1>>=
 
-plot(tab$whole.gene.dN.dS.model.0, as.numeric(as.character(tab$dginn.primate_omegaM0Bpp)), 
-     xlab="Omega Young-primate", ylab="DGINN-full's")
+<<omegaM7M8_1>>=
+tab$dginn.primate_omegaM0Bpp[tab$dginn.primate_omegaM0Bpp=="na"]<-NA
+tab$dginn.primate_omegaM0Bpp<-as.numeric(as.character(
+  tab$dginn.primate_omegaM0Bpp))
+
+plot(tab$whole.gene.dN.dS.model.0, 
+     tab$dginn.primate_omegaM0Bpp, 
+     xlab="Omega Young-primate", 
+     ylab="DGINN-full's",
+     cex=0.3)
 abline(0,1)
-abline(lm(as.numeric(as.character(tab$dginn.primate_omegaM0Bpp))~tab$whole.gene.dN.dS.model.0), col="red")
+abline(lm(tab$dginn.primate_omegaM0Bpp~tab$whole.gene.dN.dS.model.0), 
+       col="red")
 
-
-outlier<-tab[tab$whole.gene.dN.dS.model.0<0.4 & tab$dginn.primate_omegaM0Bpp>0.5,]
+outlier<-tab[tab$whole.gene.dN.dS.model.0<0.4 & 
+               tab$dginn.primate_omegaM0Bpp>0.5,]
 text(x=outlier$whole.gene.dN.dS.model.0,
 y=outlier$dginn.primate_omegaM0Bpp,
 outlier$Gene.name)
 
+outlier<-tab[tab$whole.gene.dN.dS.model.0<0.1 & 
+               tab$dginn.primate_omegaM0Bpp>0.3,]
+text(x=outlier$whole.gene.dN.dS.model.0,
+y=outlier$dginn.primate_omegaM0Bpp,
+outlier$Gene.name)  
+
+outlier<-tab[tab$whole.gene.dN.dS.model.0>0.33 & 
+               tab$dginn.primate_omegaM0Bpp<0.2,]
+text(x=outlier$whole.gene.dN.dS.model.0,
+y=outlier$dginn.primate_omegaM0Bpp,
+outlier$Gene.name)  
+
+outlier<-tab[tab$whole.gene.dN.dS.model.0>0.6 & 
+               tab$dginn.primate_omegaM0Bpp<0.6,]
+text(x=outlier$whole.gene.dN.dS.model.0,
+y=outlier$dginn.primate_omegaM0Bpp,
+outlier$Gene.name) 
 @
 
 \subsection{Janet Young's results (Young-primate) VS Cooper's result}
 
 Comparaison des Omega: colonne L "whole.gene.dN.dS.model.0" VS colonne "cooper.primates.Average\_dNdS".
-<<omegaM7M8_2>>=
 
-plot(tab$whole.gene.dN.dS.model.0, as.numeric(as.character(tab$cooper.primates.Average_dNdS)), 
-     xlab="Omega Young-primate", ylab="Omega Cooper-primate")
+<<omegaM7M8_2>>=
+tab$cooper.primates.Average_dNdS<-as.numeric(as.character(
+  tab$cooper.primates.Average_dNdS))
+
+plot(tab$whole.gene.dN.dS.model.0, 
+     tab$cooper.primates.Average_dNdS, 
+     xlab="Omega Young-primate",
+     ylab="Omega Cooper-primate",
+     cex=0.3)
 abline(0,1)
-abline(lm(as.numeric(as.character(tab$cooper.primates.Average_dNdS))~tab$whole.gene.dN.dS.model.0), col="red")
+abline(lm(tab$cooper.primates.Average_dNdS~tab$whole.gene.dN.dS.model.0), 
+       col="red")
 
+outlier<-tab[tab$whole.gene.dN.dS.model.0<0.15 & 
+               tab$cooper.primates.Average_dNdS>0.4,]
+text(x=outlier$whole.gene.dN.dS.model.0,
+y=outlier$cooper.primates.Average_dNdS,
+outlier$Gene.name, cex=0.5)
 
-outlier<-tab[tab$whole.gene.dN.dS.model.0<0.4 & tab$cooper.primates.Average_dNdS>0.5,]
+outlier<-tab[tab$whole.gene.dN.dS.model.0<0.3 & 
+               tab$cooper.primates.Average_dNdS>0.5,]
 text(x=outlier$whole.gene.dN.dS.model.0,
 y=outlier$cooper.primates.Average_dNdS,
-outlier$Gene.name)
+outlier$Gene.name, cex=0.5)
 
+outlier<-tab[tab$whole.gene.dN.dS.model.0>0.3 & 
+               tab$cooper.primates.Average_dNdS<0.1,]
+text(x=outlier$whole.gene.dN.dS.model.0,
+y=outlier$cooper.primates.Average_dNdS,
+outlier$Gene.name, cex=0.5)
 @
 
 \subsection{Cooper's results (Cooper-primate) VS DGINN-full's results}
 
 Comparaison des Omega: colonne "cooper.primates.Average\_dNdS" VS colonne "omega" dans la sortie de dginn.
-<<omegaM7M8_3>>=
 
-plot(tab$cooper.primates.Average_dNd, as.numeric(as.character(tab$dginn.primate_omegaM0Bpp)), 
-     xlab="Omega Cooper-primate", ylab="DGINN-full's")
+<<omegaM7M8_3>>=
+plot(tab$cooper.primates.Average_dNd, 
+     tab$dginn.primate_omegaM0Bpp, 
+     xlab="Omega Cooper-primate", 
+     ylab="DGINN-full's",
+     cex=0.3)
 abline(0,1)
-abline(lm(as.numeric(as.character(tab$dginn.primate_omegaM0Bpp))~tab$cooper.primates.Average_dNd), col="red")
+abline(lm(tab$dginn.primate_omegaM0Bpp~tab$cooper.primates.Average_dNd), col="red")
 
-outlier<-tab[tab$cooper.primates.Average_dNd<0.4 & tab$dginn.primate_omegaM0Bpp>0.5,]
+outlier<-tab[tab$cooper.primates.Average_dNd<0.4 & 
+               tab$dginn.primate_omegaM0Bpp>0.5,]
 text(x=outlier$cooper.primates.Average_dNd,
 y=outlier$dginn.primate_omegaM0Bpp,
-outlier$Gene.name)
-
-@
-
-
+outlier$Gene.name, cex=0.5)
 
+outlier<-tab[tab$cooper.primates.Average_dNd<0.1 & 
+               tab$dginn.primate_omegaM0Bpp>0.3,]
+text(x=outlier$cooper.primates.Average_dNd,
+y=outlier$dginn.primate_omegaM0Bpp,
+outlier$Gene.name, cex=0.5)
 
+outlier<-tab[tab$cooper.primates.Average_dNd>0.7 & 
+               tab$dginn.primate_omegaM0Bpp<0.3,]
+text(x=outlier$cooper.primates.Average_dNd,
+y=outlier$dginn.primate_omegaM0Bpp,
+outlier$Gene.name, cex=0.5)
 
+outlier<-tab[tab$cooper.primates.Average_dNd>0.45 & 
+               tab$dginn.primate_omegaM0Bpp<0.2,]
+text(x=outlier$cooper.primates.Average_dNd,
+y=outlier$dginn.primate_omegaM0Bpp,
+outlier$Gene.name, cex=0.5)
+@
 
 \section{Overlap}
 
-
 \subsection{Mondrian}
 
 <<mondrianprimates>>=
-
 library(Mondrian)
 
-#######
-
 monddata<-as.data.frame(tab$Gene.name)
 dim(monddata)
 
+dginnfulltmp<-rowSums(cbind(tab$dginn.primate_BUSTED=="Y", 
+                            tab$dginn.primate_BppM1M2=="Y", 
+                            tab$dginn.primate_BppM7M8=="Y", 
+                            tab$dginn.primate_codemlM1M2=="Y", 
+                            tab$dginn.primate_codemlM7M8=="Y")) 
 
-dginnfulltmp<-rowSums(cbind(tab$dginn.primate_BUSTED=="Y", tab$dginn.primate_BppM1M2=="Y", 
-tab$dginn.primate_BppM7M8=="Y", tab$dginn.primate_codemlM1M2=="Y", tab$dginn.primate_codemlM7M8=="Y")) 
-
-monddata$primates_young<-ifelse(tab$pVal.M8vsM7<0.05, 1, 0)
-monddata$primate_cooper<-ifelse(tab$cooper.primates.M7.M8_p_value<0.05, 1, 0)
-monddata$primates_dginn_full<-ifelse(dginnfulltmp>=3, 1,0)
+monddata$primates_young<-ifelse(
+  tab$pVal.M8vsM7<0.05, 1, 0)
+monddata$primate_cooper<-ifelse(
+  tab$cooper.primates.M7.M8_p_value<0.05, 1, 0)
+monddata$primates_dginn_full<-ifelse(
+  dginnfulltmp>=3, 1,0)
 
-mondrian(na.omit(monddata[,2:4]), labels=c("Young", "Cooper", "DGINN-full >=3" ))
+mondrian(na.omit(monddata[,2:4]), 
+         labels=c("Young", "Cooper", "DGINN-full >=3" ))
 
-#####
-monddata$primates_dginn_full<-ifelse(dginnfulltmp>=4, 1,0)
+monddata$primates_dginn_full<-ifelse(
+  dginnfulltmp>=4, 1,0)
 
-mondrian(na.omit(monddata[,2:4]), labels=c("Young", "Cooper", "DGINN-full >=4"))
+mondrian(na.omit(monddata[,2:4]), 
+         labels=c("Young", "Cooper", "DGINN-full >=4"))
 @
 
 
@@ -144,7 +202,8 @@ library(UpSetR)
 upsetdata<-as.data.frame(tab$Gene.name)
 
 upsetdata$primates_young<-ifelse(tab$pVal.M8vsM7<0.05, 1, 0)
-upsetdata$primate_cooper<-ifelse(tab$cooper.primates.M7.M8_p_value<0.05, 1, 0)
+upsetdata$primate_cooper<-ifelse(
+  tab$cooper.primates.M7.M8_p_value<0.05, 1, 0)
 upsetdata$primates_dginn_full<-ifelse(dginnfulltmp>=3, 1,0)